ISO/IEC NP 23888-8

Information technology — Artificial intelligence for multimedia — Part 8: Audio coding for machines

Апстракт

A coding format for compressing audio, multi-dimensional streams, or features extracted from such signals that is efficient in terms of bitrate/size and can be used by a network of machines after decompression to perform multiple machine analysis tasks without significantly degrading task performance. The decoded audio, multi-dimensional streams or features can be used for machine consumption or hybrid machine and human consumption. In addition to the essence the format must also contain metadata describing how the audio or multi-dimensional stream was captured and what kind of audio is captured.